Elaris Computing Nexus
A Self Adaptive Meta Learning Model for Personalized Computational Intelligence in Dynamic Problem-Solving Environments
Elaris Computing Nexus
Received On : 28 March 2026
Revised On : 06 May 2026
Accepted On : 16 May 2026
Published On : 05 June 2026
Volume 02, 2026
Pages : 080-093
Abstract
The data distributions, user preferences, and environmental factors change over time, personalized computational intelligence plays a crucial role in applications. Traditional machine learning models tend to be less effective when dealing with new tasks or problems because they need to be retrained. In this paper, a novel self-adaptive meta-learning approach is proposed to empower CIS to learn quickly from different tasks, integrate the new knowledge to enhance the performance for the evolving tasks, and transfer the knowledge to further tasks without sacrificing the personalized decision-making capability. The proposed framework combined the concept of meta-learning with an adaptive feedback mechanism which continually observes the performance of the learner with respect to the task and adjusts the learning strategies as required by changes in the environment. A lightweight knowledge adaptation module is integrated to achieve efficient real-time deployment, improve generalization and reduce computational overhead. The framework's aim is to achieve a compromise between stability and adaptability in learning, which it achieves by optimising the framework iteratively with the hope of converging quickly even when training samples are limited and the data is not stationary. Experimental testing on several benchmark datasets shows the competitiveness of the prediction performance, adaptation speed and robustness with respect to the classical deep learning and current meta-learning methods, while preserving the computational efficiency. The proposed framework is able to deal with concept drift, task heterogeneity and personalised learning needs while maintaining the property of scalability. The results show that the self-adaptive meta-learning system proposed in this paper is a practical and intelligent solution for next-generation computational intelligence system in dynamic environments, such as healthcare systems, intelligent transportation systems, cyber-physical systems, smart manufacturing systems and personalized decision support systems.
Keywords
Self-Adaptive Learning, Meta-Learning, Computational Intelligence, Personalized Learning, Dynamic Problem-Solving, Knowledge Adaptation.
- B. Chen et al., “Behavioral planning and parameter meta learning for embodied intelligence robots in adaptive assembly,” J. Ind. Inf. Integr., vol. 49, Art. no. 100995, Jan. 2026, doi: 10.1016/j.jii.2025.100995.
- B. Vijetha, “Agentic Intelligence for Unified Cyber Defense: A Self-Adaptive Framework for Threat Detection Across Cloud, Edge, and IoT Systems,” IEEE Access, vol. 14, pp. 5104–5118, 2026, doi: 10.1109/ACCESS.2026.3650833.
- Murugesh et al., “Self-evolving meta-learning neural ordinary differential equations: A novel artificial intelligence-driven approach for solving differential equations,” J. Algorithms Comput. Technol., vol. 20, May 2026, doi: 10.1177/17483026261446122.
- S. N. Bhukya, P. Raveendra Babu, E. Annapoorna, A. S. Reddy, K. Anitha, and J. Mathew, “AI-Generated Machine Learning Models: Towards an Era of Self-Evolving Intelligence,” in Proc. Int. Conf. Metaverse Current Trends Comput. (ICMCTC), Apr. 2025, pp. 1–4, doi: 10.1109/ICMCTC62214.2025.11196731.
- R. Vilalta and Y. Drissi, “A Perspective View and Survey of Meta-Learning,” Artif. Intell. Rev., vol. 18, no. 2, pp. 77–95, Jun. 2002, doi: 10.1023/A:1019956318069.
- C. Maddilety, G. Lingesh, K. S. S. Reddy, K. S. P. Reddy, and G. C. Teja, “Adaptive Learning in Non-Stationary Computer Science Environments with Self-Evolving AI Systems,” in Proc. Int. Conf. Integr. Intell. Commun. Syst. (ICIICS), Jun. 2026, pp. 1–5, doi: 10.1109/ICIICS67880.2026.11483397.
- H. M. A, L. K, and D. L, “Neuro-Semantic Federated Meta-Optimization Framework for Quantum-Assisted Predictive Congnition in Self-Evolving Cyber-Physical Infrastructures,” in Proc. Int. Conf. Autom. Comput. Renew. Syst. (ICACRS), Dec. 2025, pp. 1228–1237, doi: 10.1109/ICACRS67045.2025.11324373.
- T. Satoh, “Self-adaptive mechanism for distributed computing,” in Proc. IEEE Conf. Evolving Adaptive Intell. Syst., May 2012, pp. 11–16, doi: 10.1109/EAIS.2012.6232797.
- T. Sato, “Adaptive Resource Management in Cloud-Native Architectures Using Predictive Analytics and Reinforcement Learning Techniques,” Amer. Int. J. Comput. Sci. Technol., vol. 3, 2021, doi: 10.63282/3117-5481/AIJCST-V3I2P101.
- D. Gayathri and S. P. Shantharajah, “SAE-MRHL: A Self-Adaptive Explainable Meta-Reinforcement Hybrid Learner for remaining battery life prediction in IoE systems,” Front. Comput. Sci., vol. 8, Jul. 2026, doi: 10.3389/fcomp.2026.1884141.
- H. Guo et al., “Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning,” in Proc. Genet. Evol. Comput. Conf. (GECCO), Jul. 2025, pp. 1117–1126, doi: 10.1145/3712256.3726309.
- W. Liang, J. Wang, W. Bao, X. Zhu, Q. Wang, and B. Han, “Continuous self-adaptive optimization to learn multi-task multi-agent,” Complex Intell. Syst., vol. 8, no. 2, pp. 1355–1367, Dec. 2021, doi: 10.1007/s40747-021-00591-8.
- M. Li, Z. Dou, Y. Lin, Q. Gao, and H. Jiang, “MSAAD: Meta-Learning-Based Self-Adaptive Adversarial Defense for Specific Emitter Identification in Consumer Electronics,” IEEE Trans. Consum. Electron., vol. 72, no. 1, pp. 2243–2254, Feb. 2026, doi: 10.1109/TCE.2025.3649905.
- H. K. Krishnamurthy Sukumar, N. D. Magotra, S. P. Mokashi, S. N. R. Chintacunta, and R. Laheri, “AI-Driven Auto-Architecting of Scalable Cloud Pipelines Using Workflow Analytics and Meta-Learning,” J. Artif. Intell. Technol., May 2026, doi: 10.37965/JAIT.2026.0982.
- D. Pal, S. Bose, D. More, A. Jha, B. Banerjee, and Y. Jeppu, “MAML-SR: Self-adaptive super-resolution networks via multi-scale optimized attention-aware meta-learning,” Pattern Recognit. Lett., vol. 173, pp. 101–107, Sep. 2023, doi: 10.1016/j.patrec.2023.08.004.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
Authors thank Reviewers for taking the time and effort necessary to review the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit: https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this Article
Gunhee Gon Chun, “A Self Adaptive Meta Learning Model for Personalized Computational Intelligence in Dynamic Problem-Solving Environments”, Elaris Computing Nexus, pp. 080-093, 2026, doi: 10.65148/ECN/2026007.
Copyright
© 2026 Gunhee Gon Chun. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.